consult-session-notes

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from consulting transcripts or notes, which is then used to generate permanent records in Google Docs and the CRM.
  • Ingestion points: Input is gathered from pasted text, Google Doc links, or handoffs from the consult-transcriber skill as detailed in SKILL.md (Step 1).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the raw transcript input.
  • Capability inventory: The skill possesses the capability to write to Google Docs (mcp__google-workspace__create_doc) and update CRM notes (mcp__zynkr__update_deal).
  • Sanitization: There is no mention of sanitizing or validating the content of the transcripts before it is structured into the final summaries and filed.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes an installation command that fetches content from the author's GitHub repository.
  • Evidence: npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill consult-session-notes found in SKILL.md.
  • [COMMAND_EXECUTION]: The skill provides installation instructions utilizing a package execution command to add the skill from a remote source.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:31 PM
Security Audit — agent-trust-hub — consult-session-notes